Python framework which enables you to transform how a user calls or infers an IBM Granite model and how the output from the model is returned to the user.

A high-throughput and memory-efficient inference and serving engine for LLMs

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

We introduce the LLAMA1 Test Set, a comprehensive open-domain world knowledge QA dataset for evaluating question-answering systems. We prompted the open-source LLama-7B model for questions and shor…

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

SALMONN: Speech Audio Language Music Open Neural Network

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

[ICLR 2025] Official Code Release for Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation

Library for Textless Spoken Language Processing

🦄 Unitxt: a python library for getting data fired up and set for training and evaluation

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

Vector (and Scalar) Quantization, in Pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

Multilingual G2P in 100 languages

g2p: English Grapheme To Phoneme Conversion

IBM-Generative-AI is a Python library built on IBM's large language model REST interface to seamlessly integrate and extend this service in Python programs.

CMUdict maintenance, and tools

Active Learning on a Budget - Opposite Strategies Suit High and Low Budgets

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

A python library for self-supervised learning on images.

This is the official implementation of the method ContIG, for self-supervised learning from medical imaging with genomics

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

A python framework accelerating ML based discovery in the medical field by encouraging code reuse. Batteries included :)

K-Means clustering - constrained with minimum and maximum cluster size. Documentation: https://joshlk.github.io/k-means-constrained